{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T06:10:40Z","timestamp":1790143840176,"version":"4.0.1"},"reference-count":52,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T00:00:00Z","timestamp":1790121600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Hum. Neurosci."],"abstract":"<jats:sec>\n                    <jats:title>Introduction<\/jats:title>\n                    <jats:p>Neural speech decoding has demonstrated great potential as an alternative to current brain-computer interface (BCI) spellers, enabling a faster, more natural way of communication for patients who have lost voluntary abilities, including speech. Most neural speech decoding studies have focused on decoding cued speech, in which participants are presented with visual or auditory signals before producing imagined or overt speech. Only a few recent studies have investigated the decoding of spontaneous and intended speech without external cues using neural activity acquired from a full-scalp clinical magnetoencephalography (MEG) system. With recent advances in MEG technology, including optically pumped magnetometers (OPMs) and nitrogen-vacancy (NV) center (NV-diamond) magnetometers, MEG is emerging as a next-generation wearable system for practical speech BCIs. However, it remains unclear how many sensors are needed, where to place them, and what sampling frequency is optimal for wearable MEG devices that require cost-effective, computationally efficient operation.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>In this study, we addressed these gaps by using a forward selection algorithm to find an optimal subset of sensors for spontaneous intended and overt speech decoding and by evaluating decoding performance across different frequency bands. Support vector machine and random forest were used as the classifiers in these experiments.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Our results indicate that only a small number of sensors (7\u20138 on average, with a maximum of fewer than 24) are sufficient to achieve decoding performance comparable to that obtained using the whole scalp (more than 200) sensors. In addition, we observed that the Lower High-Gamma (62\u2013125 Hz) band yielded the best performance in some settings, although not statistically significantly higher than other bands in all settings.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Discussion<\/jats:title>\n                    <jats:p>These findings suggest that future wearable MEG devices may not need the whole-scalp sensor set and should support a sampling rate of at least 250 Hz, while 500 Hz is also encouraged, if possible. In summary, these findings provide practical insights for MEG-based BCIs for communication.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fnhum.2026.1925703","type":"journal-article","created":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:49:27Z","timestamp":1790142567000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Optimal sensor set for MEG-based spontaneous and intended speech decoding toward practical communication"],"prefix":"10.3389","volume":"20","author":[{"given":"Pedro Andres","family":"Alba Diaz","sequence":"first","affiliation":[{"name":"Department of Speech, Language, and Hearing Sciences, The University of Texas at Austin","place":["Austin, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinuk","family":"Kwon","sequence":"additional","affiliation":[{"name":"Department of Speech, Language, and Hearing Sciences, The University of Texas at Austin","place":["Austin, TX, United States"]},{"name":"Department of Neurology, The University of Texas at Austin","place":["Austin, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Karinne","family":"Berstis","sequence":"additional","affiliation":[{"name":"Department of Speech, Language, and Hearing Sciences, The University of Texas at Austin","place":["Austin, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Weed","sequence":"additional","affiliation":[{"name":"MyndVox Inc.","place":["Austin, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paul","family":"Ferrari","sequence":"additional","affiliation":[{"name":"Jack H. Miller Magnetoencephalography (MEG) Center, Helen DeVos Children's Hospital","place":["Grand Rapids, United States"]},{"name":"Department of Pediatrics and Human Development, Michigan State University","place":["Lansing, MI, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Wang","sequence":"additional","affiliation":[{"name":"Department of Speech, Language, and Hearing Sciences, The University of Texas at Austin","place":["Austin, TX, United States"]},{"name":"Department of Neurology, The University of Texas at Austin","place":["Austin, TX, United States"]},{"name":"MyndVox Inc.","place":["Austin, TX, United States"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,23]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"493","DOI":"10.1038\/s41586-019-1119-1","article-title":"Speech synthesis from neural decoding of spoken sentences","volume":"568","author":"Anumanchipalli","year":"2019","journal-title":"Nature"},{"key":"B2","doi-asserted-by":"publisher","first-page":"066014","DOI":"10.1088\/1741-2560\/10\/6\/066014","article-title":"Failure mode analysis of silicon-based intracortical microelectrode arrays in non-human primates","volume":"10","author":"Barrese","year":"2013","journal-title":"J. Neural Eng"},{"key":"B3","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1162\/nol_a_00034","article-title":"Neural decoding reveals concurrent phonemic and subphonemic representations of speech across tasks","volume":"2","author":"Beach","year":"2021","journal-title":"Neurobiol. Lang"},{"key":"B4","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1038\/nature26147","article-title":"Moving magnetoencephalography towards real-world applications with a wearable system","volume":"555","author":"Boto","year":"2018","journal-title":"Nature"},{"key":"B5","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1016\/j.neuroimage.2017.01.034","article-title":"A new generation of magnetoencephalography: room temperature measurements using optically-pumped magnetometers","volume":"149","author":"Boto","year":"2017","journal-title":"Neuroimage"},{"key":"B6","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1056\/NEJMoa2314132","article-title":"An accurate and rapidly calibrating speech neuroprosthesis","volume":"391","author":"Card","year":"2024","journal-title":"N. Engl. J. Med"},{"key":"B7","unstructured":"EEG-based discrimination of imagined speech phonemes\n          \n          201\n          206\n          \n            \n              Chi\n              X.\n            \n            \n              Hagedorn\n              J. B.\n            \n            \n              Schoonover\n              D.\n            \n            \n              D'Zmura\n              M.\n            \n          \n          Int. J. Bioelectromagn\n          13\n          2011"},{"key":"B8","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1016\/0013-4694(83)90005-6","article-title":"Demonstration of useful differences between magnetoencephalogram and electroencephalogram","volume":"56","author":"Cohen","year":"1983","journal-title":"Electroencephalogr. Clin. Neurophysiol"},{"key":"B9","doi-asserted-by":"publisher","first-page":"134","DOI":"10.1007\/978-3-030-87802-3_13","article-title":"\u201cImagined, intended, and spoken speech envelope synthesis from neuromagnetic signals,\u201d","author":"Dash","year":"","journal-title":"Speech and Computer"},{"key":"B10","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1109\/GlobalSIP.2018.8646401","article-title":"\u201cOvert speech retrieval from neuromagnetic signals using wavelets and artificial neural networks,\u201d","author":"Dash","year":"2018","journal-title":"2018 IEEE global conference on signal and information processing (GlobalSIP)"},{"key":"B11","doi-asserted-by":"publisher","first-page":"290","DOI":"10.3389\/fnins.2020.00290","article-title":"Decoding imagined and spoken phrases from non-invasive neural (MEG) signals","volume":"14","author":"Dash","year":"","journal-title":"Front. Neurosci"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/IJCNN48605.2020.9207448","article-title":"\u201cDecoding speech evoked jaw motion from non-invasive neuromagnetic oscillations,\u201d","author":"Dash","year":"","journal-title":"2020 international joint conference on neural networks (IJCNN)"},{"key":"B13","doi-asserted-by":"publisher","first-page":"1357","DOI":"10.23919\/Eusipco47968.2020.9287714","article-title":"\u201cRole of brainwaves in neural speech decoding,\u201d","author":"Dash","year":"","journal-title":"2020 28th European Signal Processing Conference (EUSIPCO)"},{"key":"B14","doi-asserted-by":"publisher","first-page":"4216","DOI":"10.1044\/2024_JSLHR-24-00046","article-title":"Neural decoding of spontaneous overt and intended speech","volume":"67","author":"Dash","year":"2024","journal-title":"J. Speech Lang. Hear. Res"},{"key":"B15","doi-asserted-by":"publisher","first-page":"182320","DOI":"10.1109\/ACCESS.2020.3028831","article-title":"MEG sensor selection for neural speech decoding","volume":"8","author":"Dash","year":"","journal-title":"IEEE Access"},{"key":"B16","doi-asserted-by":"publisher","first-page":"117969","DOI":"10.1016\/j.neuroimage.2021.117969","article-title":"Measuring the cortical tracking of speech with optically-pumped magnetometers","volume":"233","author":"de Lange","year":"2021","journal-title":"Neuroimage"},{"key":"B17","doi-asserted-by":"publisher","first-page":"383","DOI":"10.3389\/fnhum.2014.00383","article-title":"From speech to thought: the neuronal basis of cognitive units in non-experimental, real-life communication investigated using ECoG","volume":"8","author":"Derix","year":"2014","journal-title":"Front. Hum. Neurosci"},{"key":"B18","doi-asserted-by":"publisher","first-page":"40","DOI":"10.1007\/978-3-642-02574-7_5","article-title":"\u201cToward EEG sensing of imagined speech,\u201d","author":"D'Zmura","year":"2009","journal-title":"Human-Computer Interaction. New Trends"},{"key":"B19","doi-asserted-by":"publisher","first-page":"921","DOI":"10.1016\/j.neuroimage.2012.03.049","article-title":"A brief review on the history of human functional near-infrared spectroscopy (fNIRS) development and fields of application","volume":"63","author":"Ferrari","year":"2012","journal-title":"Neuroimage"},{"key":"B20","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.bspc.2019.01.006","article-title":"Transfer learning in imagined speech EEG-based BCIs","volume":"50","author":"Garcia-Salinas","year":"2019","journal-title":"Biomed. Signal Process. Control"},{"key":"B21","doi-asserted-by":"publisher","first-page":"267","DOI":"10.3389\/fnins.2013.00267","article-title":"MEG and EEG data analysis with MNE-Python","volume":"7","author":"Gramfort","year":"2013","journal-title":"Front. Neurosci"},{"key":"B22","doi-asserted-by":"publisher","first-page":"115652","DOI":"10.1016\/j.bbr.2025.115652","article-title":"An EEG-based imagined speech recognition using CSP-TP feature fusion for enhanced bci communication","volume":"493","author":"Haresh","year":"2025","journal-title":"Behav. Brain Res"},{"key":"B23","doi-asserted-by":"publisher","first-page":"429","DOI":"10.3389\/fnins.2016.00429","article-title":"Automatic speech recognition from neural signals: a focused review","volume":"10","author":"Herff","year":"2016","journal-title":"Front. Neurosci"},{"key":"B24","doi-asserted-by":"publisher","first-page":"045012","DOI":"10.1088\/1741-2552\/ac18ad","article-title":"Neural stimulation and recording performance in human sensorimotor cortex over 1500 days","volume":"18","author":"Hughes","year":"2021","journal-title":"J. Neural Eng"},{"key":"B25","doi-asserted-by":"publisher","first-page":"056032","DOI":"10.1088\/1741-2552\/acfcd9","article-title":"Single-trial classification of evoked responses to auditory tones using OPM- and SQUID-MEG","volume":"20","author":"Iivanainen","year":"2023","journal-title":"J. Neural Eng"},{"key":"B26","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1080\/2326263X.2017.1330611","article-title":"Neurolinguistic and machine-learning perspectives on direct speech BCIs for restoration of naturalistic communication","volume":"4","author":"Iljina","year":"2017","journal-title":"Brain Comput. Interfaces"},{"key":"B27","doi-asserted-by":"publisher","first-page":"1241","DOI":"10.1109\/TBME.2014.2298897","article-title":"Joint spatial-spectral feature space clustering for speech activity detection from ECoG signals","volume":"61","author":"Kanas","year":"2014","journal-title":"IEEE Trans. Biomed. Eng"},{"key":"B28","doi-asserted-by":"publisher","first-page":"1527","DOI":"10.1007\/s00415-012-6821-y","article-title":"The prevalence and characteristics of patients with classic locked-in syndrome in Dutch nursing homes","volume":"260","author":"Kohnen","year":"2013","journal-title":"J. Neurol"},{"key":"B29","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1016\/j.irbm.2021.07.001","article-title":"Brain-computer interface speller system for alternative communication: a review","volume":"43","author":"Kundu","year":"2022","journal-title":"IRBM"},{"key":"B30","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1016\/S0079-6123(05)50034-7","article-title":"The locked-in syndrome : what is it like to be conscious but paralyzed and voiceless?","volume":"150","author":"Laureys","year":"2005","journal-title":"Prog. Brain Res"},{"key":"B31","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.21105\/joss.01237","article-title":"PyWavelets: a Python package for wavelet analysis","volume":"4","author":"Lee","year":"2019","journal-title":"J. Open Source Softw"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e84296","DOI":"10.7554\/eLife.84296","article-title":"Using adversarial networks to extend brain computer interface decoding accuracy over time","volume":"12","author":"Ma","year":"2023","journal-title":"eLife"},{"key":"B33","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1016\/j.neulet.2012.08.030","article-title":"Cortical activity during speech and non-speech oromotor tasks: a magnetoencephalography (MEG) study","volume":"527","author":"Memarian","year":"2012","journal-title":"Neurosci. Lett"},{"key":"B34","doi-asserted-by":"publisher","first-page":"3096","DOI":"10.1038\/s41467-019-10994-4","article-title":"Real-time decoding of question-and-answer speech dialogue using human cortical activity","volume":"10","author":"Moses","year":"2019","journal-title":"Nat. Commun"},{"key":"B35","doi-asserted-by":"publisher","first-page":"217","DOI":"10.1056\/NEJMoa2027540","article-title":"Neuroprosthesis for decoding speech in a paralyzed person with anarthria","volume":"385","author":"Moses","year":"2021","journal-title":"N. Engl. J. Med"},{"key":"B36","doi-asserted-by":"publisher","first-page":"642251","DOI":"10.3389\/fnins.2021.642251","article-title":"Decoding covert speech from EEG-A comprehensive review","volume":"15","author":"Panachakel","year":"2021","journal-title":"Front. Neurosci"},{"key":"B37","doi-asserted-by":"publisher","first-page":"2825","DOI":"10.5555\/1953048.2078195","article-title":"Scikit-learn: machine learning in Python","volume":"12","author":"Pedregosa","year":"2011","journal-title":"J. Mach. Learn. Res"},{"key":"B38","doi-asserted-by":"publisher","first-page":"301","DOI":"10.1016\/j.neuroimage.2017.10.011","article-title":"Decoding spoken phonemes from sensorimotor cortex with high-density ECoG grids","volume":"180","author":"Ramsey","year":"2018","journal-title":"Neuroimage"},{"key":"B39","doi-asserted-by":"publisher","first-page":"57","DOI":"10.3390\/brainsci8040057","article-title":"Brain-computer interface spellers: a review","volume":"8","author":"Rezeika","year":"2018","journal-title":"Brain Sci"},{"key":"B40","doi-asserted-by":"publisher","first-page":"408","DOI":"10.1016\/j.neuroimage.2019.06.010","article-title":"Towards OPM-MEG in a virtual reality environment","volume":"199","author":"Roberts","year":"2019","journal-title":"Neuroimage"},{"key":"B41","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1109\/LifeTech52111.2021.9391883","article-title":"\u201cClassification of imagined and heard speech using amplitude spectrum and relative phase of EEG,\u201d","author":"Sakai","year":"2021","journal-title":"2021 IEEE 3rd global conference on life sciences and technologies (LifeTech)"},{"key":"B42","doi-asserted-by":"publisher","first-page":"419","DOI":"10.3389\/fnhum.2017.00419","article-title":"Functional magnetic resonance imaging and functional near-infrared spectroscopy: insights from combined recording studies","volume":"11","author":"Scarapicchia","year":"2017","journal-title":"Front. Hum. Neurosci"},{"key":"B43","doi-asserted-by":"publisher","first-page":"064010","DOI":"10.1103\/PhysRevApplied.21.064010","article-title":"Diamond quantum magnetometer with dc sensitivity of sub-10 pT Hz\u22121\/2 toward measurement of biomagnetic field","volume":"21","author":"Sekiguchi","year":"2024","journal-title":"Phys. Rev. Appl"},{"key":"B44","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1109\/JRPROC.1949.232969","article-title":"Communication in the presence of noise","volume":"37","author":"Shannon","year":"1949","journal-title":"Proc. IRE"},{"key":"B45","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1038\/s41587-020-0662-5","article-title":"Plug-and-play control of a brain-computer interface through neural map stabilization","volume":"39","author":"Silversmith","year":"2021","journal-title":"Nat. Biotechnol"},{"key":"B46","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1136\/bmj.330.7488.406","article-title":"Locked-in syndrome","volume":"330","author":"Smith","year":"2005","journal-title":"BMJ"},{"key":"B47","doi-asserted-by":"publisher","first-page":"1278","DOI":"10.1109\/EMBC.2014.6943831","article-title":"\u201cDecoding of Chinese phoneme clusters using ECoG,\u201d","author":"Song","year":"2014","journal-title":"2014 36th annual international conference of the IEEE engineering in medicine and biology society"},{"key":"B48","doi-asserted-by":"publisher","first-page":"319","DOI":"10.1007\/978-3-030-71637-0_37","article-title":"\u201cReconstruction of words, syllables, and phonemes of internal speech by EEG activity,\u201d","author":"Suyuncheva","year":"2021","journal-title":"Advances in Cognitive Research, Artificial Intelligence and Neuroinformatics"},{"key":"B49","doi-asserted-by":"publisher","first-page":"858","DOI":"10.1038\/s41593-023-01304-9","article-title":"Semantic reconstruction of continuous language from non-invasive brain recordings","volume":"26","author":"Tang","year":"2023","journal-title":"Nat. Neurosci"},{"key":"B50","doi-asserted-by":"publisher","first-page":"2013","DOI":"10.1093\/brain\/awn147","article-title":"ECoG gamma activity during a language task: differentiating expressive and receptive speech areas","volume":"131","author":"Towle","year":"2008","journal-title":"Brain"},{"key":"B51","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1056\/NEJMoa2314598","article-title":"Longevity of a brain-computer interface for amyotrophic lateral sclerosis","volume":"391","author":"Vansteensel","year":"2024","journal-title":"N. Engl. J. Med"},{"key":"B52","doi-asserted-by":"publisher","first-page":"1466","DOI":"10.1038\/s41551-025-01536-z","article-title":"Long-term unsupervised recalibration of cursor-based intracortical brain-computer interfaces using a hidden Markov model","volume":"10","author":"Wilson","year":"2026","journal-title":"Nat. Biomed. Eng"}],"container-title":["Frontiers in Human Neuroscience"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1925703\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,23]],"date-time":"2026-09-23T05:49:29Z","timestamp":1790142569000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnhum.2026.1925703\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,23]]},"references-count":52,"alternative-id":["10.3389\/fnhum.2026.1925703"],"URL":"https:\/\/doi.org\/10.3389\/fnhum.2026.1925703","relation":{},"ISSN":["1662-5161"],"issn-type":[{"value":"1662-5161","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,23]]},"article-number":"1925703"}}